AI/ML●●Solid
CRSS v0.1 – a primitive for sharing agent memory and behavior
Event sourcing for LLM context—clever approach to agent memory sharing.
Big BrainZero to One
zdilly007
104mo ago
Back to browse
GitHub Repository
ZERO.md — A universal protocol for personal AI context. Your AI knows your project. It doesn't know you. This file fixes that.
4 stars
Zero Protocol – A personal context file for AI
by DhruvKumarJha·May 20, 2026·3 points·0 comments
AI Analysis
●MidBig BrainBold Bet
Personal context file is a clever idea, but relies entirely on manual prompt injection.
Strengths
- •Standardizes the concept of a 'cognitive fingerprint' separate from project rules.
- •Portable format works across Cursor, Claude, and ChatGPT without integration.
- •Concrete examples show how it shifts AI from generic to specific advice.
Weaknesses
- •Just a markdown convention with no tooling to enforce or auto-inject context.
- •Competes with existing .cursorrules and custom instructions features.
Category
Target Audience
Developers using AI coding assistants like Cursor or Copilot
Similar To
.cursorrules · Claude Custom Instructions · AGENTS.md
Similar Projects
Infrastructure●●Solid
Open Memory Specification (OMS), Context Assembly Language (Cal)
Content-addressed agent memory with append-only CAL—delete structural impossibility, not policy.
Big BrainNiche GemZero to One
sathishmg
104mo ago
AI/ML●●Solid
OQP – A verification protocol for AI agents
OpenAPI for agent verification with risk scoring before merge — ambitious standardization play.
Bold BetBig Brain
Aamir21
823mo ago
AI/ML●●Solid
Evaluation Context Protocol (ECP)
MCP for tools, ECP for evals — protocol beats vendor lock-in for agent testing.
Big BrainShip It
aniketwattawmar
201mo ago
Developer Tools●●Solid
Unspaghettit – executable behavior specs for AI coding agents
Executable specs via MCP beat prompt drift, but Gherkin already did this for non-AI teams.
Solve My ProblemShip It
D3F
502mo ago
Productivity●Mid
The Forensic Mirror – Weaponizing LLMs for Cognitive Auditing
LLM as adversarial auditor, not assistant—but the framework lacks real tooling.
Big BrainBold Bet
llmmirror
114mo ago